{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MO3HD27JJGFWQIS6DTBV3GMK23","short_pith_number":"pith:MO3HD27J","canonical_record":{"source":{"id":"1907.05572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T04:01:57Z","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"465e72a731b1a6bd7127c5c579db55c64eea9f7f1bc066a7f8453bb85851ddbc","abstract_canon_sha256":"e6496db2ee24e19168b28b013fba885903fb950f57a0072953bf3b8d9350d864"},"schema_version":"1.0"},"canonical_sha256":"63b671ebe9498b68225e1cc35d998ad6d99794751050afb417200175fbee4421","source":{"kind":"arxiv","id":"1907.05572","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05572","created_at":"2026-05-17T23:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05572v1","created_at":"2026-05-17T23:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05572","created_at":"2026-05-17T23:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"MO3HD27JJGFW","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MO3HD27JJGFWQIS6","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MO3HD27J","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MO3HD27JJGFWQIS6DTBV3GMK23","target":"record","payload":{"canonical_record":{"source":{"id":"1907.05572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T04:01:57Z","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"465e72a731b1a6bd7127c5c579db55c64eea9f7f1bc066a7f8453bb85851ddbc","abstract_canon_sha256":"e6496db2ee24e19168b28b013fba885903fb950f57a0072953bf3b8d9350d864"},"schema_version":"1.0"},"canonical_sha256":"63b671ebe9498b68225e1cc35d998ad6d99794751050afb417200175fbee4421","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:47.870568Z","signature_b64":"XaqE2/+x/lgQtbUCVii+de5oZsUzW3SQdwoGWYu6moLf4Zw6u8eBtjHjzvUy+fqg4j9rm+gRC3BicEgGt2tjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b671ebe9498b68225e1cc35d998ad6d99794751050afb417200175fbee4421","last_reissued_at":"2026-05-17T23:40:47.869889Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:47.869889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.05572","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3V4e49WpISFn3ZXBzt9aKgICpmp7m88i9nFQJ9tdGCWX3GIh9/nczQlJy8JHOVMxA5N5qSfpoDsABf1byhw1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:29:29.060804Z"},"content_sha256":"de272872f6ce25b6be2d69e702002e0594ec42422e3d8679b6ba114763f06dff","schema_version":"1.0","event_id":"sha256:de272872f6ce25b6be2d69e702002e0594ec42422e3d8679b6ba114763f06dff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MO3HD27JJGFWQIS6DTBV3GMK23","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"R-Transformer: Recurrent Neural Network Enhanced Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.LG","authors_text":"Jiliang Tang, Yao Ma, Zhiwei Wang, Zitao Liu","submitted_at":"2019-07-12T04:01:57Z","abstract_excerpt":"Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation procedure. Therefore, many non-recurrent sequence models that are built on convolution and attention operations have been proposed recently. Notably, models with multi-head attention such as Transformer have demonstrated extreme effectiveness in capturing long-term dependencies in a variety of sequence modeling tasks. Despite their success, however, these models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05572","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RzgF9aCwFOLKb29OaWxwrO735lUCkDG/nqoDgJKJipJlv1f9/D21jMCIcnPEr0GYz+MNR8cexEn3i1cVCMPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:29:29.061455Z"},"content_sha256":"c4920fd49bc3e3b7a1eb97abaa887ff2b863de1018d604df62009ad66e91c2a7","schema_version":"1.0","event_id":"sha256:c4920fd49bc3e3b7a1eb97abaa887ff2b863de1018d604df62009ad66e91c2a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MO3HD27JJGFWQIS6DTBV3GMK23/bundle.json","state_url":"https://pith.science/pith/MO3HD27JJGFWQIS6DTBV3GMK23/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MO3HD27JJGFWQIS6DTBV3GMK23/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T01:29:29Z","links":{"resolver":"https://pith.science/pith/MO3HD27JJGFWQIS6DTBV3GMK23","bundle":"https://pith.science/pith/MO3HD27JJGFWQIS6DTBV3GMK23/bundle.json","state":"https://pith.science/pith/MO3HD27JJGFWQIS6DTBV3GMK23/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MO3HD27JJGFWQIS6DTBV3GMK23/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MO3HD27JJGFWQIS6DTBV3GMK23","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e6496db2ee24e19168b28b013fba885903fb950f57a0072953bf3b8d9350d864","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T04:01:57Z","title_canon_sha256":"465e72a731b1a6bd7127c5c579db55c64eea9f7f1bc066a7f8453bb85851ddbc"},"schema_version":"1.0","source":{"id":"1907.05572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05572","created_at":"2026-05-17T23:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05572v1","created_at":"2026-05-17T23:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05572","created_at":"2026-05-17T23:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"MO3HD27JJGFW","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MO3HD27JJGFWQIS6","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MO3HD27J","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:c4920fd49bc3e3b7a1eb97abaa887ff2b863de1018d604df62009ad66e91c2a7","target":"graph","created_at":"2026-05-17T23:40:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation procedure. Therefore, many non-recurrent sequence models that are built on convolution and attention operations have been proposed recently. Notably, models with multi-head attention such as Transformer have demonstrated extreme effectiveness in capturing long-term dependencies in a variety of sequence modeling tasks. Despite their success, however, these models ","authors_text":"Jiliang Tang, Yao Ma, Zhiwei Wang, Zitao Liu","cross_cats":["cs.CL","cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T04:01:57Z","title":"R-Transformer: Recurrent Neural Network Enhanced Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05572","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:de272872f6ce25b6be2d69e702002e0594ec42422e3d8679b6ba114763f06dff","target":"record","created_at":"2026-05-17T23:40:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e6496db2ee24e19168b28b013fba885903fb950f57a0072953bf3b8d9350d864","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T04:01:57Z","title_canon_sha256":"465e72a731b1a6bd7127c5c579db55c64eea9f7f1bc066a7f8453bb85851ddbc"},"schema_version":"1.0","source":{"id":"1907.05572","kind":"arxiv","version":1}},"canonical_sha256":"63b671ebe9498b68225e1cc35d998ad6d99794751050afb417200175fbee4421","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b671ebe9498b68225e1cc35d998ad6d99794751050afb417200175fbee4421","first_computed_at":"2026-05-17T23:40:47.869889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:47.869889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XaqE2/+x/lgQtbUCVii+de5oZsUzW3SQdwoGWYu6moLf4Zw6u8eBtjHjzvUy+fqg4j9rm+gRC3BicEgGt2tjDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:47.870568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.05572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de272872f6ce25b6be2d69e702002e0594ec42422e3d8679b6ba114763f06dff","sha256:c4920fd49bc3e3b7a1eb97abaa887ff2b863de1018d604df62009ad66e91c2a7"],"state_sha256":"8f4fb33f72db34ab73f72d051a6bf79c33cfd1e41d0ae0fc714f08cd9cdb6e08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RL9C1TPaBR75SNmClN9ldYNoU6JOAlqXxKWUxuVxLiCbf//3SsK7LfuGFzSHAFdbXVYKerBqFDuLNQGs1wslBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T01:29:29.065653Z","bundle_sha256":"f90c3c2b40f051d97b4d68a8781cd31ace31d8fdbc2da20447fcc5f679e8419b"}}